[18/24] kvm: x86/mmu: Use an rwlock for the x86 TDP MMU
diff mbox series

Message ID 20210112181041.356734-19-bgardon@google.com
State New, archived
Headers show
Series
  • Allow parallel page faults with TDP MMU
Related show

Commit Message

Ben Gardon Jan. 12, 2021, 6:10 p.m. UTC
Add a read / write lock to be used in place of the MMU spinlock when the
TDP MMU is enabled. The rwlock will enable the TDP MMU to handle page
faults in parallel in a future commit. In cases where the TDP MMU is not
in use, no operation would be acquiring the lock in read mode, so a
regular spin lock is still used as locking and unlocking a spin lock is
slightly faster.

Reviewed-by: Peter Feiner <pfeiner@google.com>

Signed-off-by: Ben Gardon <bgardon@google.com>
---
 arch/x86/include/asm/kvm_host.h |  8 ++-
 arch/x86/kvm/mmu/mmu.c          | 89 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu/mmu_internal.h |  9 ++++
 arch/x86/kvm/mmu/tdp_mmu.c      | 10 ++--
 arch/x86/kvm/x86.c              |  2 -
 virt/kvm/kvm_main.c             | 10 ++--
 6 files changed, 115 insertions(+), 13 deletions(-)

Comments

Sean Christopherson Jan. 21, 2021, 12:45 a.m. UTC | #1
On Tue, Jan 12, 2021, Ben Gardon wrote:
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index ba296ad051c3..280d7cd6f94b 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -5471,6 +5471,11 @@ void kvm_mmu_init_vm(struct kvm *kvm)
>  
>  	kvm_mmu_init_tdp_mmu(kvm);
>  
> +	if (kvm->arch.tdp_mmu_enabled)
> +		rwlock_init(&kvm->arch.mmu_rwlock);
> +	else
> +		spin_lock_init(&kvm->arch.mmu_lock);

Rather than use different lock types, what if we always use a rwlock, but only
acquire it for read when handling page faults for TDP MMUs?  That would
significantly reduce the amount of boilerplate conditionals.

The fast paths for write_lock() and spin_lock() are nearly identical, and
I would hope any differences in the slow paths are hidden in the noise.

> +
>  	node->track_write = kvm_mmu_pte_write;
>  	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
>  	kvm_page_track_register_notifier(kvm, node);
> @@ -6074,3 +6079,87 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
>  	if (kvm->arch.nx_lpage_recovery_thread)
>  		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
>  }
> +
> +void kvm_mmu_lock_shared(struct kvm *kvm)
> +{
> +	WARN_ON(!kvm->arch.tdp_mmu_enabled);
> +	read_lock(&kvm->arch.mmu_rwlock);
> +}
> +
> +void kvm_mmu_unlock_shared(struct kvm *kvm)
> +{
> +	WARN_ON(!kvm->arch.tdp_mmu_enabled);
> +	read_unlock(&kvm->arch.mmu_rwlock);
> +}
> +
> +void kvm_mmu_lock_exclusive(struct kvm *kvm)
> +{
> +	WARN_ON(!kvm->arch.tdp_mmu_enabled);
> +	write_lock(&kvm->arch.mmu_rwlock);
> +}
> +
> +void kvm_mmu_unlock_exclusive(struct kvm *kvm)
> +{
> +	WARN_ON(!kvm->arch.tdp_mmu_enabled);
> +	write_unlock(&kvm->arch.mmu_rwlock);
> +}

I'm not a fan of all of these wrappers.  It's extra layers and WARNs, and
introduces terminology that differs from the kernel's locking terminology,
e.g. read vs. shared.  The WARNs are particularly wasteful as these all have
exactly one caller that explicitly checks kvm->arch.tdp_mmu_enabled.

Even if we don't unconditionally use the rwlock, I think I'd prefer to omit
these rwlock wrappers and instead use read/write_lock directly (and drop the
WARNs). 

> +
> +void kvm_mmu_lock(struct kvm *kvm)
> +{
> +	if (kvm->arch.tdp_mmu_enabled)
> +		kvm_mmu_lock_exclusive(kvm);
> +	else
> +		spin_lock(&kvm->arch.mmu_lock);
> +}
> +EXPORT_SYMBOL_GPL(kvm_mmu_lock);
> +
> +void kvm_mmu_unlock(struct kvm *kvm)
> +{
> +	if (kvm->arch.tdp_mmu_enabled)
> +		kvm_mmu_unlock_exclusive(kvm);
> +	else
> +		spin_unlock(&kvm->arch.mmu_lock);
> +}
> +EXPORT_SYMBOL_GPL(kvm_mmu_unlock);

These exports aren't needed, I don't see any callers in kvm_intel or kvm_amd.
That's a moot point if we use rwlock unconditionally.

> +

Patch
diff mbox series

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3087de84fad3..92d5340842c8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -902,7 +902,13 @@  enum kvm_irqchip_mode {
 #define APICV_INHIBIT_REASON_X2APIC	5
 
 struct kvm_arch {
-	spinlock_t mmu_lock;
+	union {
+		/* Used if the TDP MMU is enabled. */
+		rwlock_t mmu_rwlock;
+
+		/* Used if the TDP MMU is not enabled. */
+		spinlock_t mmu_lock;
+	};
 
 	unsigned long n_used_mmu_pages;
 	unsigned long n_requested_mmu_pages;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ba296ad051c3..280d7cd6f94b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5471,6 +5471,11 @@  void kvm_mmu_init_vm(struct kvm *kvm)
 
 	kvm_mmu_init_tdp_mmu(kvm);
 
+	if (kvm->arch.tdp_mmu_enabled)
+		rwlock_init(&kvm->arch.mmu_rwlock);
+	else
+		spin_lock_init(&kvm->arch.mmu_lock);
+
 	node->track_write = kvm_mmu_pte_write;
 	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
 	kvm_page_track_register_notifier(kvm, node);
@@ -6074,3 +6079,87 @@  void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 	if (kvm->arch.nx_lpage_recovery_thread)
 		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
 }
+
+void kvm_mmu_lock_shared(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	read_lock(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_unlock_shared(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	read_unlock(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_lock_exclusive(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	write_lock(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_unlock_exclusive(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	write_unlock(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_lock(struct kvm *kvm)
+{
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_mmu_lock_exclusive(kvm);
+	else
+		spin_lock(&kvm->arch.mmu_lock);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_lock);
+
+void kvm_mmu_unlock(struct kvm *kvm)
+{
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_mmu_unlock_exclusive(kvm);
+	else
+		spin_unlock(&kvm->arch.mmu_lock);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_unlock);
+
+int kvm_mmu_lock_needbreak(struct kvm *kvm)
+{
+	if (kvm->arch.tdp_mmu_enabled)
+		return rwlock_needbreak(&kvm->arch.mmu_rwlock);
+	else
+		return spin_needbreak(&kvm->arch.mmu_lock);
+}
+
+int kvm_mmu_lock_cond_resched_exclusive(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	return cond_resched_rwlock_write(&kvm->arch.mmu_rwlock);
+}
+
+int kvm_mmu_lock_cond_resched(struct kvm *kvm)
+{
+	if (kvm->arch.tdp_mmu_enabled)
+		return kvm_mmu_lock_cond_resched_exclusive(kvm);
+	else
+		return cond_resched_lock(&kvm->arch.mmu_lock);
+}
+
+void kvm_mmu_lock_assert_held_shared(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	lockdep_assert_held_read(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_lock_assert_held_exclusive(struct kvm *kvm)
+{
+	WARN_ON(!kvm->arch.tdp_mmu_enabled);
+	lockdep_assert_held_write(&kvm->arch.mmu_rwlock);
+}
+
+void kvm_mmu_lock_assert_held(struct kvm *kvm)
+{
+	if (kvm->arch.tdp_mmu_enabled)
+		lockdep_assert_held(&kvm->arch.mmu_rwlock);
+	else
+		lockdep_assert_held(&kvm->arch.mmu_lock);
+}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index cc8268cf28d2..53a789b8a820 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -149,4 +149,13 @@  void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 
+void kvm_mmu_lock_shared(struct kvm *kvm);
+void kvm_mmu_unlock_shared(struct kvm *kvm);
+void kvm_mmu_lock_exclusive(struct kvm *kvm);
+void kvm_mmu_unlock_exclusive(struct kvm *kvm);
+int kvm_mmu_lock_cond_resched_exclusive(struct kvm *kvm);
+void kvm_mmu_lock_assert_held_shared(struct kvm *kvm);
+void kvm_mmu_lock_assert_held_exclusive(struct kvm *kvm);
+void kvm_mmu_lock_assert_held(struct kvm *kvm);
+
 #endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 1d7c01300495..8b61bdb391a0 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -59,7 +59,7 @@  static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 static inline bool tdp_mmu_next_root_valid(struct kvm *kvm,
 					   struct kvm_mmu_page *root)
 {
-	lockdep_assert_held(&kvm->mmu_lock);
+	kvm_mmu_lock_assert_held_exclusive(kvm);
 
 	if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link))
 		return false;
@@ -117,7 +117,7 @@  void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
 	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
-	kvm_mmu_lock_assert_held(kvm);
+	kvm_mmu_lock_assert_held_exclusive(kvm);
 
 	WARN_ON(root->root_count);
 	WARN_ON(!root->tdp_mmu_page);
@@ -425,7 +425,7 @@  static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
 	int as_id = kvm_mmu_page_as_id(root);
 
-	kvm_mmu_lock_assert_held(kvm);
+	kvm_mmu_lock_assert_held_exclusive(kvm);
 
 	WRITE_ONCE(*iter->sptep, new_spte);
 
@@ -1139,7 +1139,7 @@  void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 	int root_as_id;
 
-	kvm_mmu_lock_assert_held(kvm);
+	kvm_mmu_lock_assert_held_exclusive(kvm);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
@@ -1324,7 +1324,7 @@  bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 	int root_as_id;
 	bool spte_set = false;
 
-	kvm_mmu_lock_assert_held(kvm);
+	kvm_mmu_lock_assert_held_exclusive(kvm);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6cc34e8ccad..302042af87ee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10366,8 +10366,6 @@  int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (type)
 		return -EINVAL;
 
-	spin_lock_init(&kvm->arch.mmu_lock);
-
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d168bd4517d4..dcbdb3beb084 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -432,27 +432,27 @@  void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_destroy);
 
-void kvm_mmu_lock(struct kvm *kvm)
+__weak void kvm_mmu_lock(struct kvm *kvm)
 {
 	spin_lock(&kvm->arch.mmu_lock);
 }
 
-void kvm_mmu_unlock(struct kvm *kvm)
+__weak void kvm_mmu_unlock(struct kvm *kvm)
 {
 	spin_unlock(&kvm->arch.mmu_lock);
 }
 
-int kvm_mmu_lock_needbreak(struct kvm *kvm)
+__weak int kvm_mmu_lock_needbreak(struct kvm *kvm)
 {
 	return spin_needbreak(&kvm->arch.mmu_lock);
 }
 
-int kvm_mmu_lock_cond_resched(struct kvm *kvm)
+__weak int kvm_mmu_lock_cond_resched(struct kvm *kvm)
 {
 	return cond_resched_lock(&kvm->arch.mmu_lock);
 }
 
-void kvm_mmu_lock_assert_held(struct kvm *kvm)
+__weak void kvm_mmu_lock_assert_held(struct kvm *kvm)
 {
 	lockdep_assert_held(&kvm->arch.mmu_lock);
 }